Verifiable Process Rewards (VPR) converts symbolic oracles into dense turn-level supervision for reinforcement learning in agentic reasoning, outperforming outcome-only rewards and transferring to general benchmarks.
Coderl: Mastering code generation through pretrained models and deep reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Verifiable Process Rewards for Agentic Reasoning
Verifiable Process Rewards (VPR) converts symbolic oracles into dense turn-level supervision for reinforcement learning in agentic reasoning, outperforming outcome-only rewards and transferring to general benchmarks.